INDEX

Explanations

references to conditions or new rules affecting operations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hurst

-0.15

ainter

-0.15

zel

-0.14

artic

-0.14

 Reduction

-0.13

ETCH

-0.13

cq

-0.13

hear

-0.13

amin

-0.13

amy

-0.13

POSITIVE LOGITS

ei

0.17

oÄŁ

0.15

uC

0.14

uja

0.14

elp

0.14

undler

0.14

oord

0.13

 taper

0.13

fas

0.13

 Budd

0.13

Activations Density 0.548%

references to conditions or new rules affecting operations

No Comments

No Known Activations